On Wed, Nov 15, 2023 at 02:14:14AM -0500,
Xiaoyao Li <xiaoyao.li@xxxxxxxxx> wrote:
> From: Chao Peng <chao.p.peng@xxxxxxxxxxxxxxx>
>
> Switch to KVM_SET_USER_MEMORY_REGION2 when supported by KVM.
>
> With KVM_SET_USER_MEMORY_REGION2, QEMU can set up memory region that
> backend'ed both by hva-based shared memory and guest memfd based private
> memory.
>
> Signed-off-by: Chao Peng <chao.p.peng@xxxxxxxxxxxxxxx>
> Co-developed-by: Xiaoyao Li <xiaoyao.li@xxxxxxxxx>
> Signed-off-by: Xiaoyao Li <xiaoyao.li@xxxxxxxxx>
> ---
> accel/kvm/kvm-all.c | 56 ++++++++++++++++++++++++++++++++++------
> accel/kvm/trace-events | 2 +-
> include/sysemu/kvm_int.h | 2 ++
> 3 files changed, 51 insertions(+), 9 deletions(-)
>
> diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
> index 9f751d4971f8..69afeb47c9c0 100644
> --- a/accel/kvm/kvm-all.c
> +++ b/accel/kvm/kvm-all.c
> @@ -293,35 +293,69 @@ int kvm_physical_memory_addr_from_host(KVMState *s, void *ram,
> static int kvm_set_user_memory_region(KVMMemoryListener *kml, KVMSlot *slot, bool new)
> {
> KVMState *s = kvm_state;
> - struct kvm_userspace_memory_region mem;
> + struct kvm_userspace_memory_region2 mem;
> + static int cap_user_memory2 = -1;
> int ret;
>
> + if (cap_user_memory2 == -1) {
> + cap_user_memory2 = kvm_check_extension(s, KVM_CAP_USER_MEMORY2);
> + }
> +
> + if (!cap_user_memory2 && slot->guest_memfd >= 0) {
> + error_report("%s, KVM doesn't support KVM_CAP_USER_MEMORY2,"
> + " which is required by guest memfd!", __func__);
> + exit(1);
> + }
> +
> mem.slot = slot->slot | (kml->as_id << 16);
> mem.guest_phys_addr = slot->start_addr;
> mem.userspace_addr = (unsigned long)slot->ram;
> mem.flags = slot->flags;
> + mem.guest_memfd = slot->guest_memfd;
> + mem.guest_memfd_offset = slot->guest_memfd_offset;
>
> if (slot->memory_size && !new && (mem.flags ^ slot->old_flags) & KVM_MEM_READONLY) {
> /* Set the slot size to 0 before setting the slot to the desired
> * value. This is needed based on KVM commit 75d61fbc. */
> mem.memory_size = 0;
> - ret = kvm_vm_ioctl(s, KVM_SET_USER_MEMORY_REGION, &mem);
> +
> + if (cap_user_memory2) {
> + ret = kvm_vm_ioctl(s, KVM_SET_USER_MEMORY_REGION2, &mem);
> + } else {
> + ret = kvm_vm_ioctl(s, KVM_SET_USER_MEMORY_REGION, &mem);
> + }
> if (ret < 0) {
> goto err;
> }
> }
> mem.memory_size = slot->memory_size;
> - ret = kvm_vm_ioctl(s, KVM_SET_USER_MEMORY_REGION, &mem);
> + if (cap_user_memory2) {
> + ret = kvm_vm_ioctl(s, KVM_SET_USER_MEMORY_REGION2, &mem);
> + } else {
> + ret = kvm_vm_ioctl(s, KVM_SET_USER_MEMORY_REGION, &mem);
> + }
> slot->old_flags = mem.flags;
> err:
> trace_kvm_set_user_memory(mem.slot >> 16, (uint16_t)mem.slot, mem.flags,
> mem.guest_phys_addr, mem.memory_size,
> - mem.userspace_addr, ret);
> + mem.userspace_addr, mem.guest_memfd,
> + mem.guest_memfd_offset, ret);
> if (ret < 0) {
> - error_report("%s: KVM_SET_USER_MEMORY_REGION failed, slot=%d,"
> - " start=0x%" PRIx64 ", size=0x%" PRIx64 ": %s",
> - __func__, mem.slot, slot->start_addr,
> - (uint64_t)mem.memory_size, strerror(errno));
> + if (cap_user_memory2) {
> + error_report("%s: KVM_SET_USER_MEMORY_REGION2 failed, slot=%d,"
> + " start=0x%" PRIx64 ", size=0x%" PRIx64 ","
> + " flags=0x%" PRIx32 ", guest_memfd=%" PRId32 ","
> + " guest_memfd_offset=0x%" PRIx64 ": %s",
> + __func__, mem.slot, slot->start_addr,
> + (uint64_t)mem.memory_size, mem.flags,
> + mem.guest_memfd, (uint64_t)mem.guest_memfd_offset,
> + strerror(errno));
> + } else {
> + error_report("%s: KVM_SET_USER_MEMORY_REGION failed, slot=%d,"
> + " start=0x%" PRIx64 ", size=0x%" PRIx64 ": %s",
> + __func__, mem.slot, slot->start_addr,
> + (uint64_t)mem.memory_size, strerror(errno));
> + }
> }
> return ret;
> }
> @@ -477,6 +511,9 @@ static int kvm_mem_flags(MemoryRegion *mr)
> if (readonly && kvm_readonly_mem_allowed) {
> flags |= KVM_MEM_READONLY;
> }
> + if (memory_region_has_guest_memfd(mr)) {
> + flags |= KVM_MEM_PRIVATE;
> + }
Nitpick: it was renamed to KVM_MEM_GUEST_MEMFD
As long as the value is defined to same value, it doesn't matter, though.
--
Isaku Yamahata <isaku.yamahata@xxxxxxxxxxxxxxx>
